Discrimination-aware data mining

By Dino Pedreschi, Salvatore Ruggieri, Franco Turini. 2008

795 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

Citations in the corpus

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (2016, background): “However, similar issues arise, such as direct and indirect bias [29].”
Towards fairer datasets: filtering and balancing the distribution of the people subtree in the ImageNet hierarchy (2019, background): “Algorithmic solutions have ranged from removing undesired bias by preprocessing the data [39, 59], striking a tradeoff between performance and fairness by posing additional regularization during training or inference [34, 40, 52, 80, 81, 83], or designing application-specific interventions (such as…”
Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems (2018, methodology): “on measuring discrimination in data as well as on evaluating performance of discrimination-aware predictive models (Zliobaite, 2015; Pedreshi et al., 2008; Hajian and Domingo-Ferrer, 2013; Goh et al., 2016).”
Equality of Opportunity in Supervised Learning (2016, background): “Early work of Pedreshi et al. [PRT08] and several follow-up works explore a logical rule-based approach to non-discrimination.”
Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “learning processes (DLPs), which allow the use of sensitive variables during model building but not prediction, are either sub- or equi-optimal [102, 64, 66, 67, 131].”
Local Rule-Based Explanations of Black Box Decision Systems (2018, background): “n explanation for what one considers a biased decision is a profound drawback of learning from big data, limiting social acceptance and trust on its adoption in many sensitive contexts. Starting from [29] a rich literature has been flourishing on discrimination discovery and avoidance. Some of the i”
A Survey of Methods for Explaining Black Box Models (2018, background): “Training a classifier on historical datasets, reporting human decisions, could lead to the discovery of endemic preconceptions [88].”
On formalizing fairness in prediction with machine learning (2017, background): “However, satisfying fairness through unawareness is not a sufficient condition to avoid discrimination when other background knowledge is available (33).”
Interpretability via Model Extraction (2017, background): “model could reconstruct that feature from other features [22].”
Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classification (2017, positive): “This was expressed quite eloquently by Pedreshi et al. 19 in a prescient paper written nearly a decade ago: [L]earning from historical data may mean to discover traditional prejudices that are endemic in reality, and to assign to such practices the status of general rules, maybe unconsciously, as…”
Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models (2016, background): “Increasingly, the emerging subﬁeld around the topic is known as discrimination aware data mining, or fairness aware data mining (Pedreshi et al., 2008).”
Data preprocessing techniques for classification without discrimination (2011, background): “In Discrimination-Aware Data Mining two main directions can be distinguished: detection of discrimination [21–24], and the direction followed in this paper, namely learning classifiers if the data are discriminatory [4,15].”
Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms (2019, background): “proposed to extract from the dataset classification rules which represent certain discrimination patterns [3], [13], [14].”
Efficient candidate screening under multiple tests and implications for fairness (2019, background): “In the more recent literature on fairness in machine learning, researchers often focus on binary classification, with employees characterized by a protected characteristic (group membership), and other (non-protected) covariates [15, 11, 12].”
Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, background): “The ﬁrst line of research in this domain focuses on identifying discrimination in the data (Pedreshi, Ruggieri, and Turini 2008) or in the model (Adler et al. 2018).”
Aequitas: A Bias and Fairness Audit Toolkit (2018, background): “.nature.com/articles/d41586-018-05469-3 4. http://aequitas.dssg.io/ 2 Aequitas: A Bias and Fairness Audit Toolkit 2. Related Work Fairness has been dened has being being accountable on the treatment Pedreshi et al. (2008); Dwork et al. (2012); Luong et al. (2011); Calders and Zliobaite_ (2013); Hard”
The Price of Fair PCA: One Extra Dimension (2018, neutral): “Other work has developed techniques to obfuscate a sensitive attribute directly [Pedreshi et al., 2008; Kamiran et al., 2010; Calders and Verwer, 2010; Kamiran and Calders, 2011; Luong et al., 2011; Kamiran et al., 2012; Kamishima et al., 2012; Hajian and Domingo-Ferrer, 2013; Feldman et al., 2015;…”
The Frontiers of Fairness in Machine Learning (2018, background): ““Fairness and transparency” transformed from a niche topic with a trickle of papers produced every year (at least since the work of [PRT08]) to a major subﬁeld of machine learning, complete with a dedicated archival conference (ACM FAT*).”
Taking Advantage of Multitask Learning for Fair Classification (2018, background): “From a statistical perspective, sensitive information can improve model performance: removing this information may result in a less accurate model, without necessarily improving the fairness of the solution, [17, 29, 36].”